Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kyle_grove
on Nov 10, 2019
|
parent
|
context
|
favorite
| on:
Deep learning has a size problem
In fact, one of the chief advantages of the BERT/Transformer architecture over ELMO/LSTM is the ability to parallelize.
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
